R Notebook

Run download_data.Rmd and niche_resiliance.Rmd First!

library(randomForest)
library(reshape2)
library(rpart)

fetch_city_niche_data_for <- function(pool_name) {
  results_filename <- paste(paste(pool_name, 'city', 'niche', 'resilience', 'intercept', sep = "_"), "csv", sep = ".")
  results <- read_csv(results_filename)
  
  joined <- left_join(city_data, results)
  
  pool_size_col_name <- paste(pool_name, 'pool', 'size', sep = "_")
  
  joined[,c("response", pool_size_col_name, "population_growth", "rainfall_monthly_min", "rainfall_annual_average", "rainfall_monthly_max", "temperature_annual_average", "temperature_monthly_min", "temperature_monthly_max", "happiness_negative_effect", "happiness_positive_effect", "happiness_future_life", "number_of_biomes", "realm", "biome_name", "region_20km_includes_estuary", "region_50km_includes_estuary", "region_100km_includes_estuary", "city_includes_estuary", "region_20km_average_pop_density", "region_50km_average_pop_density", "region_100km_average_pop_density", "city_max_pop_density", "city_average_pop_density", "mean_population_exposure_to_pm2_5_2019", "region_20km_cultivated", "region_20km_urban", "region_50km_cultivated", "region_50km_urban", "region_100km_cultivated", "region_100km_urban", "region_20km_elevation_delta", "region_20km_mean_elevation", "region_50km_elevation_delta", "region_50km_mean_elevation", "region_100km_elevation_delta", "region_100km_mean_elevation", "city_elevation_delta", "city_mean_elevation", "urban", "shrubs", "permanent_water", "open_forest", "herbaceous_wetland", "herbaceous_vegetation", "cultivated", "closed_forest", "share_of_population_within_400m_of_open_space", "percentage_urban_area_as_streets", "percentage_urban_area_as_open_public_spaces_and_streets", "percentage_urban_area_as_open_public_spaces", "city_gdp_per_population")]
}

merlin_city_niche_data <- fetch_city_niche_data_for('merlin')

── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  name = col_character(),
  response = col_double()
)

Joining, by = "name"

merlin_city_niche_data

merlin_city_niche_data_fixed <- rfImpute(response ~ ., merlin_city_niche_data)

     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |    7.716    90.32 |
     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |    7.925    92.76 |
     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |    7.911    92.60 |
     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |    7.897    92.43 |
     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |     7.94    92.94 |

merlin_city_niche_data_fixed

source('./random_forest_selection_functions.R')

select_variables_from_random_forest(merlin_city_niche_data_fixed)

 [1] "merlin_pool_size"                                        "region_100km_cultivated"                                 "region_20km_elevation_delta"                            
 [4] "region_50km_cultivated"                                  "region_50km_elevation_delta"                             "city_mean_elevation"                                    
 [7] "temperature_monthly_min"                                 "region_20km_cultivated"                                  "city_elevation_delta"                                   
[10] "rainfall_annual_average"                                 "herbaceous_vegetation"                                   "rainfall_monthly_max"                                   
[13] "temperature_annual_average"                              "region_100km_urban"                                      "shrubs"                                                 
[16] "region_100km_elevation_delta"                            "region_50km_urban"                                       "region_50km_mean_elevation"                             
[19] "percentage_urban_area_as_open_public_spaces"             "share_of_population_within_400m_of_open_space"           "population_growth"                                      
[22] "region_20km_mean_elevation"                              "city_gdp_per_population"                                 "happiness_future_life"                                  
[25] "city_average_pop_density"                                "region_100km_mean_elevation"                             "happiness_positive_effect"                              
[28] "happiness_negative_effect"                               "open_forest"                                             "cultivated"                                             
[31] "region_20km_urban"                                       "percentage_urban_area_as_open_public_spaces_and_streets" "percentage_urban_area_as_streets"                       
[34] "rainfall_monthly_min"                                    "closed_forest"                                           "herbaceous_wetland"                                     
[37] "mean_population_exposure_to_pm2_5_2019"                  "realm"                                                   "temperature_monthly_max"                                
[40] "permanent_water"                                         "region_100km_average_pop_density"                        "biome_name"                                             
[43] "region_50km_average_pop_density"                         "urban"                                                  

select_variables_from_random_forest(merlin_city_niche_data_fixed_single_scale)

 [1] "merlin_pool_size"                                        "region_100km_cultivated"                                 "region_20km_elevation_delta"                            
 [4] "city_elevation_delta"                                    "temperature_monthly_min"                                 "rainfall_annual_average"                                
 [7] "city_mean_elevation"                                     "temperature_annual_average"                              "herbaceous_vegetation"                                  
[10] "rainfall_monthly_max"                                    "percentage_urban_area_as_open_public_spaces"             "population_growth"                                      
[13] "region_50km_mean_elevation"                              "city_gdp_per_population"                                 "region_100km_urban"                                     
[16] "happiness_future_life"                                   "share_of_population_within_400m_of_open_space"           "happiness_positive_effect"                              
[19] "city_average_pop_density"                                "open_forest"                                             "herbaceous_wetland"                                     
[22] "closed_forest"                                           "percentage_urban_area_as_open_public_spaces_and_streets" "temperature_monthly_max"                                
[25] "rainfall_monthly_min"                                    "mean_population_exposure_to_pm2_5_2019"                  "percentage_urban_area_as_streets"                       
[28] "realm"                                                   "region_100km_average_pop_density"                        "biome_name"                                             
[31] "urban"                                                  

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size")])

[1] "Mean  9.83324185545329 , SD:  0.108020977220518 , Mean + SD:  9.94126283267381"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated")])

[1] "Mean  7.99232355039231 , SD:  0.0987346598244752 , Mean + SD:  8.09105821021678"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta")])

[1] "Mean  7.71884750365334 , SD:  0.0943463048624823 , Mean + SD:  7.81319380851582"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta")])

[1] "Mean  7.28832737463507 , SD:  0.118323120312041 , Mean + SD:  7.40665049494711"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta", "temperature_monthly_min")])

[1] "Mean  7.27158846954248 , SD:  0.107283578951765 , Mean + SD:  7.37887204849425"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta", "temperature_monthly_min", "rainfall_annual_average")])

[1] "Mean  7.5616033792135 , SD:  0.126098274518769 , Mean + SD:  7.68770165373227"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta", "temperature_monthly_min", "rainfall_annual_average", "city_mean_elevation")])

[1] "Mean  7.54793220768361 , SD:  0.115157862948407 , Mean + SD:  7.66309007063202"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta", "temperature_monthly_min", "rainfall_annual_average", "city_mean_elevation", "temperature_annual_average")])

[1] "Mean  7.46427345093566 , SD:  0.093643141044835 , Mean + SD:  7.55791659198049"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta", "temperature_monthly_min", "rainfall_annual_average", "city_mean_elevation", "temperature_annual_average", "herbaceous_vegetation")])

[1] "Mean  7.56274983640729 , SD:  0.121591185124118 , Mean + SD:  7.6843410215314"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta", "temperature_monthly_min", "rainfall_annual_average", "city_mean_elevation", "temperature_annual_average", "herbaceous_vegetation", "rainfall_monthly_max")])

[1] "Mean  7.46064178123067 , SD:  0.125271345448836 , Mean + SD:  7.5859131266795"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta", "temperature_monthly_min", "rainfall_annual_average", "city_mean_elevation", "temperature_annual_average", "herbaceous_vegetation", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces")])

[1] "Mean  7.50642622702775 , SD:  0.144544442364443 , Mean + SD:  7.65097066939219"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta", "temperature_monthly_min", "rainfall_annual_average", "city_mean_elevation", "temperature_annual_average", "herbaceous_vegetation", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "population_growth")])

[1] "Mean  7.64483741960505 , SD:  0.138937152566949 , Mean + SD:  7.783774572172"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta", "temperature_monthly_min", "rainfall_annual_average", "city_mean_elevation", "temperature_annual_average", "herbaceous_vegetation", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "population_growth", "region_50km_mean_elevation")])

[1] "Mean  7.552523713242 , SD:  0.100685892278421 , Mean + SD:  7.65320960552042"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta", "temperature_monthly_min", "rainfall_annual_average", "city_mean_elevation", "temperature_annual_average", "herbaceous_vegetation", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "population_growth", "region_50km_mean_elevation", "city_gdp_per_population")])

[1] "Mean  7.4149688424601 , SD:  0.123149153234689 , Mean + SD:  7.53811799569479"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta", "temperature_monthly_min", "rainfall_annual_average", "city_mean_elevation", "temperature_annual_average", "herbaceous_vegetation", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "population_growth", "region_50km_mean_elevation", "city_gdp_per_population", "region_100km_urban")])

[1] "Mean  7.35531696631406 , SD:  0.119488604784723 , Mean + SD:  7.47480557109878"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta", "temperature_monthly_min", "rainfall_annual_average", "city_mean_elevation", "temperature_annual_average", "herbaceous_vegetation", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "population_growth", "region_50km_mean_elevation", "city_gdp_per_population", "region_100km_urban", "happiness_future_life")])

[1] "Mean  7.32642899186827 , SD:  0.116615705755584 , Mean + SD:  7.44304469762385"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta", "temperature_monthly_min", "rainfall_annual_average", "city_mean_elevation", "temperature_annual_average", "herbaceous_vegetation", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "population_growth", "region_50km_mean_elevation", "city_gdp_per_population", "region_100km_urban", "happiness_future_life", "share_of_population_within_400m_of_open_space")])

[1] "Mean  7.33029167138504 , SD:  0.151379813068732 , Mean + SD:  7.48167148445377"

create_fifty_rows_of_oob(merlin_city_niche_data_fixed[,c("response", "merlin_pool_size", "region_100km_cultivated", "region_20km_elevation_delta", "city_elevation_delta", "temperature_monthly_min", "rainfall_annual_average", "city_mean_elevation", "temperature_annual_average", "herbaceous_vegetation", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "population_growth", "region_50km_mean_elevation", "city_gdp_per_population", "region_100km_urban", "happiness_future_life", "share_of_population_within_400m_of_open_space", "happiness_positive_effect")])

[1] "Mean  7.33982125967019 , SD:  0.146517453948112 , Mean + SD:  7.4863387136183"

“merlin_pool_size”, “region_100km_cultivated”, “region_20km_elevation_delta”, “city_elevation_delta”

birdlife_city_niche_data <- fetch_city_niche_data_for('birdlife')

── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  name = col_character(),
  response = col_double()
)

Joining, by = "name"

birdlife_city_niche_data

birdlife_city_niche_data_fixed <- rfImpute(response ~ ., birdlife_city_niche_data)

     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |    4.102    90.27 |
     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |    3.933    86.54 |
     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |    4.123    90.72 |
     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |    4.101    90.25 |
     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |    4.034    88.78 |

birdlife_city_niche_data_fixed

select_variables_from_random_forest(birdlife_city_niche_data_fixed)

 [1] "region_100km_cultivated"                                 "region_20km_elevation_delta"                             "happiness_future_life"                                  
 [4] "birdlife_pool_size"                                      "biome_name"                                              "herbaceous_wetland"                                     
 [7] "region_50km_cultivated"                                  "region_50km_elevation_delta"                             "temperature_annual_average"                             
[10] "temperature_monthly_min"                                 "shrubs"                                                  "region_100km_elevation_delta"                           
[13] "region_20km_cultivated"                                  "share_of_population_within_400m_of_open_space"           "rainfall_monthly_max"                                   
[16] "percentage_urban_area_as_open_public_spaces"             "region_50km_mean_elevation"                              "city_mean_elevation"                                    
[19] "temperature_monthly_max"                                 "region_20km_mean_elevation"                              "rainfall_annual_average"                                
[22] "city_elevation_delta"                                    "happiness_negative_effect"                               "cultivated"                                             
[25] "region_20km_urban"                                       "mean_population_exposure_to_pm2_5_2019"                  "percentage_urban_area_as_open_public_spaces_and_streets"
[28] "rainfall_monthly_min"                                    "happiness_positive_effect"                               "open_forest"                                            
[31] "city_gdp_per_population"                                 "region_100km_urban"                                      "population_growth"                                      
[34] "city_max_pop_density"                                    "region_100km_average_pop_density"                        "permanent_water"                                        
[37] "region_50km_urban"                                       "city_average_pop_density"                                "region_100km_mean_elevation"                            
[40] "percentage_urban_area_as_streets"                        "region_20km_average_pop_density"                         "closed_forest"                                          
[43] "urban"                                                   "realm"                                                   "herbaceous_vegetation"                                  

select_variables_from_random_forest(birdlife_city_niche_data_fixed_single_scale)

 [1] "region_100km_cultivated"                       "region_20km_elevation_delta"                   "birdlife_pool_size"                           
 [4] "happiness_future_life"                         "biome_name"                                    "herbaceous_wetland"                           
 [7] "temperature_annual_average"                    "shrubs"                                        "temperature_monthly_min"                      
[10] "rainfall_monthly_max"                          "percentage_urban_area_as_open_public_spaces"   "share_of_population_within_400m_of_open_space"
[13] "temperature_monthly_max"                       "city_elevation_delta"                          "rainfall_annual_average"                      
[16] "city_mean_elevation"                           "happiness_negative_effect"                     "region_20km_urban"                            
[19] "region_50km_mean_elevation"                    "mean_population_exposure_to_pm2_5_2019"        "open_forest"                                  
[22] "rainfall_monthly_min"                          "happiness_positive_effect"                     "city_max_pop_density"                         
[25] "population_growth"                             "percentage_urban_area_as_streets"              "urban"                                        
[28] "realm"                                        

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated")])

[1] "Mean  4.50386961689022 , SD:  0.0363565048630193 , Mean + SD:  4.54022612175324"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta")])

[1] "Mean  4.36902358064174 , SD:  0.0581432582983119 , Mean + SD:  4.42716683894005"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size")])

[1] "Mean  4.13678414086199 , SD:  0.0626975679061028 , Mean + SD:  4.19948170876809"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life")])

[1] "Mean  3.74317703463414 , SD:  0.0677633847986711 , Mean + SD:  3.81094041943281"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life", "biome_name")])

[1] "Mean  3.64353483615936 , SD:  0.0611563723900384 , Mean + SD:  3.70469120854939"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life", "biome_name", "herbaceous_wetland")])

[1] "Mean  3.40676311044889 , SD:  0.0598605598854249 , Mean + SD:  3.46662367033432"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life", "biome_name", "herbaceous_wetland", "temperature_annual_average")])

[1] "Mean  3.45831836593852 , SD:  0.053060794067478 , Mean + SD:  3.511379160006"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life", "biome_name", "herbaceous_wetland", "temperature_annual_average", "shrubs")])

[1] "Mean  3.49022830536913 , SD:  0.0489040922860873 , Mean + SD:  3.53913239765522"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life", "biome_name", "herbaceous_wetland", "temperature_annual_average", "shrubs", "temperature_monthly_min")])

[1] "Mean  3.48105288061014 , SD:  0.0517672797451502 , Mean + SD:  3.53282016035529"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life", "biome_name", "herbaceous_wetland", "temperature_annual_average", "shrubs", "temperature_monthly_min", "rainfall_monthly_max")])

[1] "Mean  3.50761152189195 , SD:  0.0689289548904812 , Mean + SD:  3.57654047678243"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life", "biome_name", "herbaceous_wetland", "temperature_annual_average", "shrubs", "temperature_monthly_min", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces")])

[1] "Mean  3.60844812567458 , SD:  0.0611350997446665 , Mean + SD:  3.66958322541924"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life", "biome_name", "herbaceous_wetland", "temperature_annual_average", "shrubs", "temperature_monthly_min", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "share_of_population_within_400m_of_open_space")])

[1] "Mean  3.59585050445119 , SD:  0.0635466826542851 , Mean + SD:  3.65939718710547"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life", "biome_name", "herbaceous_wetland", "temperature_annual_average", "shrubs", "temperature_monthly_min", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "share_of_population_within_400m_of_open_space", "temperature_monthly_max")])

[1] "Mean  3.61618249759617 , SD:  0.0692672194985198 , Mean + SD:  3.68544971709469"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life", "biome_name", "herbaceous_wetland", "temperature_annual_average", "shrubs", "temperature_monthly_min", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "share_of_population_within_400m_of_open_space", "temperature_monthly_max", "city_elevation_delta")])

[1] "Mean  3.63655868532768 , SD:  0.0678297596829471 , Mean + SD:  3.70438844501063"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life", "biome_name", "herbaceous_wetland", "temperature_annual_average", "shrubs", "temperature_monthly_min", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "share_of_population_within_400m_of_open_space", "temperature_monthly_max", "city_elevation_delta", "rainfall_annual_average")])

[1] "Mean  3.67696512583789 , SD:  0.0634939923748381 , Mean + SD:  3.74045911821273"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life", "biome_name", "herbaceous_wetland", "temperature_annual_average", "shrubs", "temperature_monthly_min", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "share_of_population_within_400m_of_open_space", "temperature_monthly_max", "city_elevation_delta", "rainfall_annual_average", "city_mean_elevation")])

[1] "Mean  3.67857319022986 , SD:  0.0570183020765647 , Mean + SD:  3.73559149230643"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life", "biome_name", "herbaceous_wetland", "temperature_annual_average", "shrubs", "temperature_monthly_min", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "share_of_population_within_400m_of_open_space", "temperature_monthly_max", "city_elevation_delta", "rainfall_annual_average", "city_mean_elevation", "happiness_negative_effect")])

[1] "Mean  3.68302331543985 , SD:  0.074173907354739 , Mean + SD:  3.75719722279459"

create_fifty_rows_of_oob(birdlife_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "birdlife_pool_size", "happiness_future_life", "biome_name", "herbaceous_wetland", "temperature_annual_average", "shrubs", "temperature_monthly_min", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "share_of_population_within_400m_of_open_space", "temperature_monthly_max", "city_elevation_delta", "rainfall_annual_average", "city_mean_elevation", "happiness_negative_effect", "region_20km_urban")])

[1] "Mean  3.68666059556525 , SD:  0.0710454862910919 , Mean + SD:  3.75770608185634"

“region_100km_cultivated”, “region_20km_elevation_delta”, “birdlife_pool_size”, “happiness_future_life”, “biome_name”, “herbaceous_wetland”

select_variables_from_random_forest(either_city_niche_data_fixed)

 [1] "region_100km_cultivated"                                 "region_50km_cultivated"                                  "region_20km_elevation_delta"                            
 [4] "either_pool_size"                                        "region_20km_cultivated"                                  "herbaceous_wetland"                                     
 [7] "biome_name"                                              "temperature_monthly_min"                                 "region_50km_elevation_delta"                            
[10] "city_mean_elevation"                                     "cultivated"                                              "happiness_future_life"                                  
[13] "temperature_annual_average"                              "city_gdp_per_population"                                 "shrubs"                                                 
[16] "city_elevation_delta"                                    "share_of_population_within_400m_of_open_space"           "region_100km_elevation_delta"                           
[19] "temperature_monthly_max"                                 "region_100km_urban"                                      "rainfall_monthly_min"                                   
[22] "rainfall_monthly_max"                                    "region_50km_mean_elevation"                              "region_20km_mean_elevation"                             
[25] "percentage_urban_area_as_open_public_spaces"             "mean_population_exposure_to_pm2_5_2019"                  "open_forest"                                            
[28] "region_50km_urban"                                       "realm"                                                   "city_average_pop_density"                               
[31] "happiness_positive_effect"                               "region_100km_mean_elevation"                             "rainfall_annual_average"                                
[34] "region_100km_average_pop_density"                        "closed_forest"                                           "region_50km_average_pop_density"                        
[37] "happiness_negative_effect"                               "population_growth"                                       "city_max_pop_density"                                   
[40] "permanent_water"                                         "percentage_urban_area_as_streets"                        "percentage_urban_area_as_open_public_spaces_and_streets"
[43] "herbaceous_vegetation"                                   "urban"                                                  

select_variables_from_random_forest(either_city_niche_data_fixed_single_scale)

 [1] "region_100km_cultivated"                                 "region_20km_elevation_delta"                             "either_pool_size"                                       
 [4] "cultivated"                                              "herbaceous_wetland"                                      "temperature_monthly_min"                                
 [7] "temperature_annual_average"                              "biome_name"                                              "happiness_future_life"                                  
[10] "city_elevation_delta"                                    "city_mean_elevation"                                     "city_gdp_per_population"                                
[13] "temperature_monthly_max"                                 "shrubs"                                                  "rainfall_monthly_max"                                   
[16] "share_of_population_within_400m_of_open_space"           "region_50km_mean_elevation"                              "region_100km_urban"                                     
[19] "percentage_urban_area_as_open_public_spaces"             "open_forest"                                             "rainfall_monthly_min"                                   
[22] "mean_population_exposure_to_pm2_5_2019"                  "happiness_positive_effect"                               "city_average_pop_density"                               
[25] "rainfall_annual_average"                                 "realm"                                                   "population_growth"                                      
[28] "city_max_pop_density"                                    "percentage_urban_area_as_open_public_spaces_and_streets" "herbaceous_vegetation"                                  
[31] "urban"                                                  

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated")])

[1] "Mean  5.47839397140055 , SD:  0.0428281713065628 , Mean + SD:  5.52122214270711"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta")])

[1] "Mean  5.05342072230863 , SD:  0.0746941734987245 , Mean + SD:  5.12811489580736"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size")])

[1] "Mean  4.94203335623192 , SD:  0.0571663399503317 , Mean + SD:  4.99919969618225"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated")])

[1] "Mean  4.59021498680249 , SD:  0.0718464001879054 , Mean + SD:  4.6620613869904"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland")])

[1] "Mean  4.27509360760281 , SD:  0.0661371106610057 , Mean + SD:  4.34123071826381"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min")])

[1] "Mean  4.21171943190095 , SD:  0.0645794056393035 , Mean + SD:  4.27629883754025"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average")])

[1] "Mean  4.28641440265764 , SD:  0.0614627099891406 , Mean + SD:  4.34787711264678"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average", "biome_name")])

[1] "Mean  4.23618919822712 , SD:  0.0548445818017577 , Mean + SD:  4.29103378002888"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average", "biome_name", "happiness_future_life")])

[1] "Mean  4.15066566339542 , SD:  0.0644687882920083 , Mean + SD:  4.21513445168743"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average", "biome_name", "happiness_future_life", "city_elevation_delta")])

[1] "Mean  4.14640207833858 , SD:  0.0705190195642546 , Mean + SD:  4.21692109790283"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average", "biome_name", "happiness_future_life", "city_elevation_delta", "city_mean_elevation")])

[1] "Mean  4.07030645833854 , SD:  0.0667827729649328 , Mean + SD:  4.13708923130347"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average", "biome_name", "happiness_future_life", "city_elevation_delta", "city_mean_elevation", "city_gdp_per_population")])

[1] "Mean  4.00101494842476 , SD:  0.0710341509145194 , Mean + SD:  4.07204909933928"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average", "biome_name", "happiness_future_life", "city_elevation_delta", "city_mean_elevation", "city_gdp_per_population", "temperature_monthly_max")])

[1] "Mean  4.03830493077006 , SD:  0.0715126350934185 , Mean + SD:  4.10981756586348"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average", "biome_name", "happiness_future_life", "city_elevation_delta", "city_mean_elevation", "city_gdp_per_population", "temperature_monthly_max", "shrubs")])

[1] "Mean  4.03422891144653 , SD:  0.0570291338854217 , Mean + SD:  4.09125804533196"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average", "biome_name", "happiness_future_life", "city_elevation_delta", "city_mean_elevation", "city_gdp_per_population", "temperature_monthly_max", "shrubs", "rainfall_monthly_max")])

[1] "Mean  4.05696327010979 , SD:  0.0655155247424855 , Mean + SD:  4.12247879485227"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average", "biome_name", "happiness_future_life", "city_elevation_delta", "city_mean_elevation", "city_gdp_per_population", "temperature_monthly_max", "shrubs", "rainfall_monthly_max", "share_of_population_within_400m_of_open_space")])

[1] "Mean  4.0512495472162 , SD:  0.0706656194437637 , Mean + SD:  4.12191516665996"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average", "biome_name", "happiness_future_life", "city_elevation_delta", "city_mean_elevation", "city_gdp_per_population", "temperature_monthly_max", "shrubs", "rainfall_monthly_max", "share_of_population_within_400m_of_open_space", "region_50km_mean_elevation")])

[1] "Mean  4.05618548495902 , SD:  0.058518977036564 , Mean + SD:  4.11470446199558"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average", "biome_name", "happiness_future_life", "city_elevation_delta", "city_mean_elevation", "city_gdp_per_population", "temperature_monthly_max", "shrubs", "rainfall_monthly_max", "share_of_population_within_400m_of_open_space", "region_50km_mean_elevation", "region_100km_urban")])

[1] "Mean  4.02195820758833 , SD:  0.0753422076360216 , Mean + SD:  4.09730041522435"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average", "biome_name", "happiness_future_life", "city_elevation_delta", "city_mean_elevation", "city_gdp_per_population", "temperature_monthly_max", "shrubs", "rainfall_monthly_max", "share_of_population_within_400m_of_open_space", "region_50km_mean_elevation", "region_100km_urban", "percentage_urban_area_as_open_public_spaces")])

[1] "Mean  4.06331944292818 , SD:  0.0589151462504439 , Mean + SD:  4.12223458917862"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average", "biome_name", "happiness_future_life", "city_elevation_delta", "city_mean_elevation", "city_gdp_per_population", "temperature_monthly_max", "shrubs", "rainfall_monthly_max", "share_of_population_within_400m_of_open_space", "region_50km_mean_elevation", "region_100km_urban", "percentage_urban_area_as_open_public_spaces", "open_forest")])

[1] "Mean  4.08573713674715 , SD:  0.0721002310687971 , Mean + SD:  4.15783736781595"

create_fifty_rows_of_oob(either_city_niche_data_fixed[,c("response", "region_100km_cultivated", "region_20km_elevation_delta", "either_pool_size", "cultivated", "herbaceous_wetland", "temperature_monthly_min", "temperature_annual_average", "biome_name", "happiness_future_life", "city_elevation_delta", "city_mean_elevation", "city_gdp_per_population", "temperature_monthly_max", "shrubs", "rainfall_monthly_max", "share_of_population_within_400m_of_open_space", "region_50km_mean_elevation", "region_100km_urban", "percentage_urban_area_as_open_public_spaces", "open_forest", "rainfall_monthly_min")])

[1] "Mean  4.08949195449016 , SD:  0.0599449818742405 , Mean + SD:  4.1494369363644"

“region_100km_cultivated”, “region_20km_elevation_delta”, “either_pool_size”, “cultivated”, “herbaceous_wetland”, “temperature_monthly_min”, “temperature_annual_average”, “biome_name”, “happiness_future_life”, “city_elevation_delta”, “city_mean_elevation”, “city_gdp_per_population”

both_city_niche_data <- fetch_city_niche_data_for('both')

── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  name = col_character(),
  response = col_double()
)

Joining, by = "name"

both_city_niche_data

both_city_niche_data_fixed <- rfImpute(response ~ ., both_city_niche_data)

     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |    7.417    94.67 |
     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |    7.665    97.84 |
     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |    7.487    95.57 |
     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |    7.514    95.91 |
     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
 300 |    7.189    91.77 |

both_city_niche_data_fixed

select_variables_from_random_forest(both_city_niche_data_fixed)

 [1] "region_100km_cultivated"                                 "temperature_monthly_min"                                 "region_50km_cultivated"                                 
 [4] "region_20km_elevation_delta"                             "both_pool_size"                                          "region_50km_elevation_delta"                            
 [7] "city_elevation_delta"                                    "rainfall_annual_average"                                 "percentage_urban_area_as_open_public_spaces"            
[10] "region_20km_cultivated"                                  "rainfall_monthly_max"                                    "shrubs"                                                 
[13] "percentage_urban_area_as_streets"                        "biome_name"                                              "temperature_annual_average"                             
[16] "happiness_future_life"                                   "city_mean_elevation"                                     "region_100km_elevation_delta"                           
[19] "region_50km_urban"                                       "cultivated"                                              "closed_forest"                                          
[22] "region_20km_urban"                                       "share_of_population_within_400m_of_open_space"           "herbaceous_wetland"                                     
[25] "happiness_negative_effect"                               "region_50km_mean_elevation"                              "open_forest"                                            
[28] "temperature_monthly_max"                                 "region_100km_urban"                                      "region_20km_mean_elevation"                             
[31] "herbaceous_vegetation"                                   "city_average_pop_density"                                "city_gdp_per_population"                                
[34] "happiness_positive_effect"                               "rainfall_monthly_min"                                    "mean_population_exposure_to_pm2_5_2019"                 
[37] "percentage_urban_area_as_open_public_spaces_and_streets" "permanent_water"                                         "urban"                                                  
[40] "region_100km_average_pop_density"                        "region_20km_average_pop_density"                         "region_100km_mean_elevation"                            
[43] "region_50km_average_pop_density"                         "population_growth"                                       "city_max_pop_density"                                   
[46] "realm"                                                  

select_variables_from_random_forest(both_city_niche_data_fixed_single_scale)

 [1] "region_100km_cultivated"                                 "both_pool_size"                                          "temperature_monthly_min"                                
 [4] "region_20km_elevation_delta"                             "city_elevation_delta"                                    "rainfall_annual_average"                                
 [7] "rainfall_monthly_max"                                    "percentage_urban_area_as_open_public_spaces"             "temperature_annual_average"                             
[10] "biome_name"                                              "happiness_future_life"                                   "shrubs"                                                 
[13] "percentage_urban_area_as_streets"                        "cultivated"                                              "region_50km_urban"                                      
[16] "city_mean_elevation"                                     "closed_forest"                                           "herbaceous_wetland"                                     
[19] "happiness_negative_effect"                               "share_of_population_within_400m_of_open_space"           "temperature_monthly_max"                                
[22] "open_forest"                                             "city_average_pop_density"                                "herbaceous_vegetation"                                  
[25] "mean_population_exposure_to_pm2_5_2019"                  "happiness_positive_effect"                               "region_50km_mean_elevation"                             
[28] "rainfall_monthly_min"                                    "percentage_urban_area_as_open_public_spaces_and_streets" "urban"                                                  
[31] "region_100km_average_pop_density"                        "population_growth"                                       "city_max_pop_density"                                   
[34] "realm"                                                  

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated")])

[1] "Mean  7.89974031313127 , SD:  0.0798297471087301 , Mean + SD:  7.97957006024"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size")])

[1] "Mean  7.84200259775259 , SD:  0.130631478885126 , Mean + SD:  7.97263407663772"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min")])

[1] "Mean  7.43699623508042 , SD:  0.119837524694346 , Mean + SD:  7.55683375977477"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta")])

[1] "Mean  7.23579107124848 , SD:  0.123613064510451 , Mean + SD:  7.35940413575894"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta")])

[1] "Mean  7.05337203570387 , SD:  0.113312350336365 , Mean + SD:  7.16668438604024"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average")])

[1] "Mean  7.31525919898467 , SD:  0.123982967537266 , Mean + SD:  7.43924216652194"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max")])

[1] "Mean  7.24103640359564 , SD:  0.101804530106879 , Mean + SD:  7.34284093370252"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces")])

[1] "Mean  7.1175442871678 , SD:  0.117921741421446 , Mean + SD:  7.23546602858925"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "temperature_annual_average")])

[1] "Mean  7.07490875026318 , SD:  0.120627196895919 , Mean + SD:  7.1955359471591"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "temperature_annual_average", "biome_name")])

[1] "Mean  7.13767809433254 , SD:  0.119982229541574 , Mean + SD:  7.25766032387412"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "temperature_annual_average", "biome_name", "happiness_future_life")])

[1] "Mean  7.02628026731596 , SD:  0.120857576790716 , Mean + SD:  7.14713784410668"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "temperature_annual_average", "biome_name", "happiness_future_life", "shrubs")])

[1] "Mean  7.00230947783711 , SD:  0.12470886455917 , Mean + SD:  7.12701834239628"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "temperature_annual_average", "biome_name", "happiness_future_life", "shrubs", "percentage_urban_area_as_streets")])

[1] "Mean  7.08562802954228 , SD:  0.104552312634745 , Mean + SD:  7.19018034217702"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "temperature_annual_average", "biome_name", "happiness_future_life", "shrubs", "percentage_urban_area_as_streets", "cultivated")])

[1] "Mean  7.00513864532854 , SD:  0.112554636288927 , Mean + SD:  7.11769328161746"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "temperature_annual_average", "biome_name", "happiness_future_life", "shrubs", "percentage_urban_area_as_streets", "cultivated", "region_50km_urban")])

[1] "Mean  6.96287993217581 , SD:  0.109890720881233 , Mean + SD:  7.07277065305704"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "temperature_annual_average", "biome_name", "happiness_future_life", "shrubs", "percentage_urban_area_as_streets", "cultivated", "region_50km_urban", "city_mean_elevation")])

[1] "Mean  6.94249024014476 , SD:  0.133225982636121 , Mean + SD:  7.07571622278088"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "temperature_annual_average", "biome_name", "happiness_future_life", "shrubs", "percentage_urban_area_as_streets", "cultivated", "region_50km_urban", "city_mean_elevation", "closed_forest")])

[1] "Mean  6.98552556448999 , SD:  0.106651887371854 , Mean + SD:  7.09217745186185"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "temperature_annual_average", "biome_name", "happiness_future_life", "shrubs", "percentage_urban_area_as_streets", "cultivated", "region_50km_urban", "city_mean_elevation", "closed_forest", "herbaceous_wetland")])

[1] "Mean  6.93603304672847 , SD:  0.110718406224751 , Mean + SD:  7.04675145295322"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "temperature_annual_average", "biome_name", "happiness_future_life", "shrubs", "percentage_urban_area_as_streets", "cultivated", "region_50km_urban", "city_mean_elevation", "closed_forest", "herbaceous_wetland", "happiness_negative_effect")])

[1] "Mean  6.94189353817021 , SD:  0.108959461997887 , Mean + SD:  7.0508530001681"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "temperature_annual_average", "biome_name", "happiness_future_life", "shrubs", "percentage_urban_area_as_streets", "cultivated", "region_50km_urban", "city_mean_elevation", "closed_forest", "herbaceous_wetland", "happiness_negative_effect", "share_of_population_within_400m_of_open_space")])

[1] "Mean  6.97285898270068 , SD:  0.123369469358957 , Mean + SD:  7.09622845205964"

create_fifty_rows_of_oob(both_city_niche_data_fixed[,c("response", "region_100km_cultivated", "both_pool_size", "temperature_monthly_min", "region_20km_elevation_delta", "city_elevation_delta", "rainfall_annual_average", "rainfall_monthly_max", "percentage_urban_area_as_open_public_spaces", "temperature_annual_average", "biome_name", "happiness_future_life", "shrubs", "percentage_urban_area_as_streets", "cultivated", "region_50km_urban", "city_mean_elevation", "closed_forest", "herbaceous_wetland", "happiness_negative_effect", "share_of_population_within_400m_of_open_space", "temperature_monthly_max")])

[1] "Mean  6.99293124494808 , SD:  0.115407935480152 , Mean + SD:  7.10833918042823"

“region_100km_cultivated”, “both_pool_size”, “temperature_monthly_min”, “region_20km_elevation_delta”, “city_elevation_delta”

So….

“merlin_pool_size”, “region_100km_cultivated”, “region_20km_elevation_delta”, “city_elevation_delta” “region_100km_cultivated”, “region_20km_elevation_delta”, “birdlife_pool_size”, “happiness_future_life”, “biome_name”, “herbaceous_wetland” “region_100km_cultivated”, “region_20km_elevation_delta”, “either_pool_size”, “cultivated”, “herbaceous_wetland”, “temperature_monthly_min”, “temperature_annual_average”, “biome_name”, “happiness_future_life”, “city_elevation_delta”, “city_mean_elevation”, “city_gdp_per_population” “region_100km_cultivated”, “both_pool_size”, “temperature_monthly_min”, “region_20km_elevation_delta”, “city_elevation_delta”